We study how vision-language models trained on Internet-scale data can b...
We describe a system for deep reinforcement learning of robotic manipula...
By transferring knowledge from large, diverse, task-agnostic datasets, m...
Large language models can encode a wealth of semantic knowledge about th...
In order to be effective general purpose machines in real world environm...
We explore possible methods for multi-task transfer learning which seek ...
We consider the problem of learning useful robotic skills from previousl...
One of the great promises of robot learning systems is that they will be...
Meta-reinforcement learning algorithms can enable robots to acquire new
...
Simulation-to-real transfer is an important strategy for making reinforc...
Recent advancements in machine learning research have given rise to recu...
We present a novel solution to the problem of simulation-to-real transfe...